Skip to main content
Glama

getecoback-raumklima

gebrauchtgeraet_schatten_kamerawinkel_gegenprobe

Read-only

Eine auffällige Stelle bei zwei Blickrichtungen und veränderter Beleuchtung als Beobachtung einordnen — Separate a reproducible mark from a view-dependent appearance.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "gleiche_stelle": "<gleiche_stelle>",
      "blick_a": "<blick_a>",
      "blick_b": "<blick_b>",
      "sicht_bei_lichtwechsel": "<sicht_bei_lichtwechsel>"
    },
    "name": "gebrauchtgeraet_schatten_kamerawinkel_gegenprobe"
  }
}

Input Schema

NameRequiredDescriptionDefault
blick_aYesWar sie bei Blickrichtung A sichtbar?
blick_bYesWar sie bei Blickrichtung B sichtbar?
gleiche_stelleYesIst dieselbe Stelle ohne Verschieben des Teils eindeutig wiedergefunden?
sicht_bei_lichtwechselYesBlieb sie bei dokumentiert veränderter Beleuchtung sichtbar?

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and locality are covered without description help. The description adds the classification intent — the judgment is about reproducibility versus view dependence — but says nothing about what is returned, whether a single verdict or more, or what happens when the inputs are inconsistent (e.g. visible in A but not B). Enough added value to sit above the annotation baseline, not enough to be rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short clauses, one per language, with the decisive contrast ('reproducible mark' vs 'view-dependent appearance') placed at the end where it lands. No filler sentences. The bilingual duplication costs a little density but is not wasteful given the German parameter names.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With four required booleans fully documented in the schema and a read-only annotation set, the inputs are adequately covered. The gap is on the outcome side: there is no output schema and the description never says what the tool produces — a classification, a confidence, a flag — so the agent cannot anticipate the result shape. For a judgment tool this is a meaningful omission but not a blocking one.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four booleans are already self-documenting in German. The description reinforces which parameters matter (two view directions, changed lighting) and frames the shared purpose of the four checks, but it adds no interpretation rule such as how conflicting blick_a/blick_b values should be read. Baseline 3 is appropriate where the schema carries the semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The German clause names a concrete operation ('als Beobachtung einordnen') on a concrete object ('eine auffällige Stelle bei zwei Blickrichtungen und veränderter Beleuchtung'), and the English gloss states the discriminating goal: separate a reproducible mark from a view-dependent appearance. An agent can tell this is a shadow/reflection-versus-defect judgment rather than a generic inspection. It does not name a sibling to distinguish itself from, so it stops short of 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the scenario 'two viewing directions plus changed lighting', which tells the agent the situation in which the tool applies. There are no explicit when-not conditions and no named alternatives (e.g. a surface-trace tool) for the case where the mark is a real physical trace rather than a lighting artifact. The agent must infer the boundary from the topic alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources